Building a bridge of bounding box regression between oriented and horizontal object detection in remote sensing images

X Qian, B Wu, G Cheng, X Yao… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Oriented object detection (OOD) aims to precisely detect the objects with arbitrary orientation
in remote sensing images (RSIs). Up to now, most of the bounding box regression (BBR) …

Instance-aware distillation for efficient object detection in remote sensing images

C Li, G Cheng, G Wang, P Zhou… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Practical applications ask for object detection models that achieve high performance at low
overhead. Knowledge distillation demonstrates favorable potential in this case by …

A unified transformer framework for group-based segmentation: Co-segmentation, co-saliency detection and video salient object detection

Y Su, J Deng, R Sun, G Lin, H Su… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Humans tend to mine objects by learning from a group of images or several frames of video
since we live in a dynamic world. In the computer vision area, many researchers focus on co …

Mining high-quality pseudoinstance soft labels for weakly supervised object detection in remote sensing images

X Qian, Y Huo, G Cheng, C Gao… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Weakly supervised object detection in remote sensing images (RSI) is still a challenge
because of the lack of instance-level labels, and many existing methods have two problems …

[HTML][HTML] Semantic segmentation guided pseudo label mining and instance re-detection for weakly supervised object detection in remote sensing images

X Qian, C Li, W Wang, X Yao, G Cheng - International Journal of Applied …, 2023 - Elsevier
Weakly supervised object detection (WSOD) in remote sensing images (RSIs) has good
practical value because it only requires the image-level annotations. The existing methods …

Dynamic low-rank and sparse priors constrained deep autoencoders for hyperspectral anomaly detection

S Lin, M Zhang, X Cheng, L Shi… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Linear-based low-rank and sparse models (LRSM) and nonlinear-based deep autoencoder
(DAE) models have been proven to be effective for the task of anomaly detection (AD) in …

ECAE: Edge-aware class activation enhancement for semisupervised remote sensing image semantic segmentation

W Miao, Z Xu, J Geng, W Jiang - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Remote sensing image semantic segmentation (RSISS) remains challenging due to the
scarcity of labeled data. Semisupervised learning can leverage pseudolabels to enhance …

Multiform ensemble self-supervised learning for few-shot remote sensing scene classification

J Li, M Gong, H Liu, Y Zhang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Self-supervised learning is an effective way to solve model collapse for few-shot remote
sensing scene classification (FSRSSC). However, most self-supervised contrastive learning …

Hyperspectral anomaly detection via sparse representation and collaborative representation

S Lin, M Zhang, X Cheng, K Zhou… - IEEE Journal of …, 2022 - ieeexplore.ieee.org
Sparse representation (SR)-based approaches and collaborative representation (CR)-
based methods are proved to be effective to detect the anomalies in a hyperspectral image …

Smooth giou loss for oriented object detection in remote sensing images

X Qian, N Zhang, W Wang - Remote Sensing, 2023 - mdpi.com
Oriented object detection (OOD) can more accurately locate objects with an arbitrary
direction in remote sensing images (RSIs) compared to horizontal object detection. The most …